Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Metabolomics datasets used in the study.

More »

Table 1 Expand

Fig 1.

Metabolomics workflow and SHAP methodology.

A: A metabolomics workflow that culminates with model training for predictive or regression purposes. B: SHAP allows for local and global interpretations of model predictions. Explanations are made locally, and because of the additivity property of Shapley values, the methods allow for global interpretations. C: A sample calculation of Shapley values of a feature xi.

More »

Fig 1 Expand

Fig 2.

Machine learning pipeline.

PLS-DA: Partial Least Square Discriminant Analysis; XGBoost: Extreme Gradient Boosting; VIP: Variable Importance in Projection.

More »

Fig 2 Expand

Table 2.

Machine learning performance.

More »

Table 2 Expand

Fig 3.

Global feature importance and feature importance correlations.

A: PLS-DA VIP score plot. B: SHAP bar plot. C: Scatterplot of the VIP score and the mean(|SHAP value|) with a Pearson’s correlation coefficient of 0.50. D: Scatterplot of the Gini importance score and the mean(|SHAP value|) with a Pearson’s correlation coefficient of 0.99.

More »

Fig 3 Expand

Fig 4.

SHAP summary plot.

A: SHAP summary plots showing the importance of all metabolomic features. B: SHAP summary plot illustration with testosterone glucuronide and p-Anisic acid.

More »

Fig 4 Expand

Fig 5.

SHAP embedding plots.

A: Embeddings plot highlighting testosterone glucuronide. B: Embeddings plot highlighting Ketoleucine.

More »

Fig 5 Expand

Fig 6.

Local explanations of a representative sample.

A: Force plot showing a male prediction. B: Waterfall plot displaying the same prediction.

More »

Fig 6 Expand

Fig 7.

SHAP for error analysis.

A: Confusion matrix of the test set for the MTBLS404 dataset. Waterfall plots of, B and C: True positive representative samples, and D: A false negative sample.

More »

Fig 7 Expand

Fig 8.

Error analysis with SHAP for true negative and false positive samples.

A and B: True negative representative samples. C and D: False positive samples.

More »

Fig 8 Expand